© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11479
    Prev
    Next
    INDEX
    Explanations

    phrases related to invitations or engagement in activities among a specific audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.88
     MonoBehaviour
    -0.79
     GenerationType
    -0.71
    ]")]
    -0.70
    ngrx
    -0.70
    DockStyle
    -0.64
    XmlAccessType
    -0.64
    ValueGenerated
    -0.62
     ExecuteAsync
    -0.62
    ChildScrollView
    -0.61
    POSITIVE LOGITS
     vocês
    0.63
     you
    0.59
    FYI
    0.59
     FYI
    0.55
     Note
    0.55
    breviation
    0.55
     revés
    0.52
    diğim
    0.52
     kalian
    0.51
    万一
    0.51
    Activations Density 0.307%

    No Known Activations